Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    510
    -0.15
    ÃŃn
    -0.15
    uis
    -0.15
    UIS
    -0.15
     ÑĨи
    -0.15
     عÙĨد
    -0.15
    ÃŃm
    -0.15
     Afghanistan
    -0.15
    sez
    -0.14
    cheid
    -0.14
    POSITIVE LOGITS
     Cake
    0.26
    Cake
    0.24
    cake
    0.22
     cake
    0.22
    .ct
    0.17
     Williamson
    0.17
     userModel
    0.17
     Paginator
    0.17
     Inf
    0.17
     Bake
    0.16
    Act Density 0.001%

    No Known Activations